Use Cases
Natural storytelling voices with proper prosody for long-form listening experiences.
For long-form narration, prioritize 'Multi-lingual' or 'HD' voices. Use SSML to add subtle pauses (<break time='200ms'/>) between paragraphs and use the 'Express-as' tag for emotional storytelling.
Selected based on style variety, language support, and audio quality.
HD Flash version of Yunhan, with English and Chinese bilingual capability, clear, energetic, and youthful, with a moderate pace and friendly tone, and rich emotions, suitable for podcast, chat, audiobook, narration that requires a positive and engaging delivery.
zh-CN-Yunhan:DragonHDFlashLatestNeural A HD version of Seraphina, a casually charming voice, ideal for both casual chats and audiobooks, offering a relaxed yet engaging tone.
de-DE-Seraphina:DragonHDLatestNeural A generally calm and relaxed voice that can switch between tones seamlessly and be highly expressive when needed.
en-US-DavisNeural A lively and warm voice with multiple scenario styles and emotions.
zh-CN-XiaoxiaoNeural A cheerful, friendly, and emotional voice, bringing warmth and feeling to every interaction.
zh-CN-YunxiaNeural HD version of Steffan with a wider range of styles, perfectly suited for audiobook narration and storytelling.
en-US-Steffan:DragonHDLatestNeural